Mortality prediction among ICU inpatients based on MIMIC-III database results from the conditional medical generative adversarial network

Abstract

Background and aims: Improved mortality prediction among intensive care unit (ICU) inpatients is a valuable and challenging task. Limited clinical data, especially with appropriate labels, are an important element restricting accurate predictions. Generative adversarial networks (GANs) are excellent generative models and have shown great potential for data simulation. However, there have been no relevant studies using GANs to predict mortality among ICU inpatients. In this study, we aim to evaluate the predictive performance of a variant of GAN called conditional medical GAN (c-med GAN) compared with some baseline models, including simplified acute physiology score II (SAPS II), support vector machine (SVM), and multilayer perceptron (MLP).

Methods: Data from a publicly available intensive care database, the Medical Information Mart for Intensive Care III (MIMIC-III) database (v1.4), were included in this study. The area under the precision-recall curve (PR-AUC), area under the receiver operating characteristic curve (ROC-AUC), and F1 score were used to evaluate the predictive performance. In addition, the size of the dataset was artificially reduced, and the performance of the c-med GAN was compared in different size datasets.

Results: The results showed that c-med GAN achieves the best PR-AUC, ROC-AUC, and F1 score compared with SAPS II, SVM, and MLP when training in the full MIMIC-III dataset. When the size of the dataset was reduced, the prediction performances of both MLP and c-med GAN were affected. However, the c-med GAN still outperformed MLP on smaller datasets and had less degradation.

Conclusion: The prediction of in-hospital mortality based on the c-med GAN for ICU patients showed better performance than the baseline models. Despite some inadequacies, this model may have a promising future in clinical applications which will be explored by further research.

Keywords: C-med GAN; GAN; MIMIC-III; Mortality prediction; ROC-AUC.

Fig. 1

Multilayer perceptron.

Fig. 2

GAN and conditional medical GAN (c-med GAN). (A) Basic GAN. The generator (G) network generates fake data from the random variable Z. The discriminator (D) network distinguishes between fake data and real data. In constant iterations, G is able to generate fake data that even D cannot distinguish from the real data. (B) Autoencoder network in the c-med GAN. The features and labels were extracted separately from the original data and put into the encoder module to produce the intermediate vector V. The intermediate vector V and labels were then put into the decoder module for training. The goal of training is to reproduce the output features identical to the input features. (C) Adversarial networks in the c-med GAN. G first generated variables V', with the same dimensionality as the intermediate variables V in the autoencoder, from the random variable Z. Then, V' was put into the trained decoder module together with the given labels to generate the fake features. Eventually, the given labels and fake features were put into D along with the labels and features of the real data to discriminate their authenticity. The goal of training is to enable G to generate fake data with labels that D cannot distinguish from the real data.

Fig. 3

The workflow the of pipeline used in this study.

Fig. 4

Comparison of some basic characters between real and fake data in datasets. The fake data were generated by thec-med GAN. The small and medium datasets included 10% and 50% of patients in the full dataset, respectively.

Fig. 5

Comparison of the predictive performance between different models. A. Receiver operating characteristic curve, B. precision-recall curve, C. calibration curve.

Fig. 6

Comparison between the multilayer perceptron and c-med GAN in the different size datasets. A. receiver operating characteristic curve in the full dataset, B. receiver operating characteristic curve in the small dataset, C. receiver operating characteristic curve in the medium dataset. D. precision-recall curve in the full dataset, E. precision-recall curve in the small dataset, F. precision-recall curve in the medium dataset.